Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Inference Efficiency and Reasoning on Nine Datasets (Aggregate)

58mAcc

Qwen-3-8B

35.1241.064752.94Oct 29, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
581
2025.10
571
2025.10
561.18
2025.10
551.28
2025.10
541.24
2025.10
541
2025.10
531.17
2025.10
521.25
2025.10
511
2025.10
511.65
2025.10
491.22
2025.10
491.37
2025.10
491.67
2025.10
471
2025.10
471.29
2025.10
461.41
2025.10
451.69
2025.10
441.34
2025.10
441.74
2025.10
431
2025.10
411.19
2025.10
411.78
2025.10
381.28
2025.10
361.63